New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Verify In Browser

by voyager-crew in voyager-crew/voyager

Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis.

GPL-3.0Auto-check passedDevelopment

Install Verify In Browser

skills CLI
$ npx skills add voyager-crew/voyager --skill verify-in-browser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install voyager-crew/voyager verify-in-browser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/voyager-crew/voyager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/verify-in-browser .claude/skills/verify-in-browser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
verify-in-browser
GitHub stars
20k
Token cost
~886 tokens
SKILL.md length
511 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
GPL-3.0

At a glance

Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis.

  • Works in 5 steps: Identify the affected browser, installed… → Build or refresh the artifact that… → Reload the extension using an available… → …
  • Tasks that involve Browser extensions
  • SKILL.md covers Load the intended build, Read and measure the page, Gemini shapes that make static… and Before you finish
  • Calls bun

What it does

Verify In Browser is an agent skill from voyager-crew/voyager. Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Browser extensions. It works with Chrome Extensions. The repository describes itself as: Enhancement suite for Gemini, AI Studio, Claude, ChatGPT & DeepSeek — plus a prompt manager for any website, DeepSeek Harness included. / 面向 Gemini、AI Studio、Claude、ChatGPT 与… The licence is GPL-3.0.

When your agent uses it

  • Tasks that involve Browser extensions

Example prompts

  • “/verify-in-browser”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the affected browser, installed Voyager extension, its loaded directory, and the target tab (including the user's reported tab…
  2. Build or refresh the artifact that browser actually loads: Chrome development uses bun run dev:chrome / dist_chrome_dev; production…
  3. Reload the extension using an available extension-management tool or the browser UI. With Chrome DevTools, list_extensions identifies…
  4. Refresh the target content-script tab so it runs the updated code. Check for unsent input or an active response before refreshing…
  5. Confirm a build-specific marker or changed behavior in that tab before collecting evidence. An extension reload alone does not replace…

What it can do on your machine

Read from SKILL.md and the folder at commit dfb08a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Verify In Browser loads about 886 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~886

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from voyager-crew/voyager at commit dfb08a6, republished under its GPL-3.0 licence (© voyager-crew). 511 words, ~886 tokens.

Download SKILL.mdSave it as .claude/skills/verify-in-browser/SKILL.md (or your agent's skills folder).
name
verify-in-browser
description
Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis.
metadata.version
1.0.0

Verify a content-script change in a live browser

Unit fixtures cannot prove the current host DOM matches our assumptions. If the first fix fails, inspect the real DOM and loaded build before editing again.

Load the intended build

  1. Identify the affected browser, installed Voyager extension, its loaded directory, and the target tab (including the user's reported tab when diagnosing stale behavior).
  2. Build or refresh the artifact that browser actually loads: Chrome development uses bun run dev:chrome / dist_chrome_dev; production verification uses bun run build:chrome / dist_chrome. Use AGENTS.md for cross-browser build requirements. Reuse an existing build if its relevant inputs are unchanged.
  3. Reload the extension using an available extension-management tool or the browser UI. With Chrome DevTools, list_extensions identifies Voyager and reload_extension reloads it. Use another available tool/UI route if these are absent; request manual reload only when no available capability can do it. Safari uses update-safari-extension.
  4. Refresh the target content-script tab so it runs the updated code. Check for unsent input or an active response before refreshing; preserve that state or use a disposable test tab until the target can be refreshed safely. Reload additional tabs only when the requested workflow needs them.
  5. Confirm a build-specific marker or changed behavior in that tab before collecting evidence. An extension reload alone does not replace content scripts already running in open tabs.

If the user was seeing an old build, verify their reported tab too when safe; a new test tab alone does not resolve that report. Distinguish refreshing a test session from implementing normal conversation navigation, which must preserve the native navigation rules in AGENTS.md.

Show full SKILL.md (243 more words)Show less

Read and measure the page

Use the available DOM/browser tools. Compare actual selectors, text, computed styles and lifecycle behavior against the assumption under test; record the first mismatch and enough surrounding DOM to explain it. Keep conversation content private in shared evidence.

A temporary element can test a new CSS rule when that rule distinguishes the build; remove the probe afterward. Use an actual new marker from this change, rather than copying an unrelated class from an old fix.

Gemini shapes that make static reasoning wrong

Each of these cost a wrong fix before it was measured.

  • A user turn's textContent is not the message. The bubble also carries a screen-reader "You said" prefix and the copy/edit/expand controls, which render through a Material Symbols icon font whose glyph is the element's text — so the string gains literal words like content_copy. Read .query-text-line.
  • A long turn is collapsed, not truncated: all 62 lines sit in the DOM behind a CSS height clamp and an expand chevron. Do not design around recovering text that is already there.
  • Text typed after a slash token lands on the prompt's own last line, with no newline between them. Anything that assumes a line boundary between the template and the person's words never fires.

Before you finish

  • State what you verified in the browser and what you only inferred. If the extension could not be reloaded, the check did not happen — say so.
  • Close any tab this session created.

© voyager-crew, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/verify-in-browser of voyager-crew/voyager.

Open the folder on GitHubat commit dfb08a6

Compare with similar skills

Verify In Browser next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Verify In Browser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify In Browser this skillvoyager-crew/voyager20k—~886Automated safety check: PassGPL-3.0
Wxt Browser Extensionsvantezzen/skip-silence4692 repos~1.9kAutomated safety check: PassMIT
Kimi WebbridgeMoonshotAI/kimi-code7.8k—~3.6kAutomated safety check: PassMIT
Repomix Browser Extension Developeryamadashy/repomix29k1 repos~288Automated safety check: PassMIT
Deepseek Automationzhu1090093659/deepseek-pp1.9k—~2.1kAutomated safety check: NotesApache-2.0
Live Extension UI Automationqixing-jk/all-api-hub4.9k—~2.6kAutomated safety check: PassAGPL-3.0

Similar skills

  • Wxt Browser Extensions

    vantezzen/skip-silence

    WXT browser extension performance optimization guidelines. An agent skill from vantezzen/skip-silence.

    469 GitHub starsUsed in 2 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Kimi Webbridge

    MoonshotAI/kimi-code

    Kimi Browser Extension（Kimi 浏览器扩展，原 Kimi WebBridge）lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login…

    7.8k GitHub stars~3.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Repomix Browser Extension Developer

    yamadashy/repomix

    Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content…

    29k GitHub starsUsed in 1 repo~288 tokens
    DevelopmentAuto-check passed

  • Deepseek Automation

    zhu1090093659/deepseek-pp

    A skill your agent uses when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

  • Live Extension UI Automation

    qixing-jk/all-api-hub

    Control, debug, and test the live dev browser extension UI (Options, Popup, Sidepanel) via CDP with persistent login states and accounts.

    4.9k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Knockoff Release Shipper

    Shpigford/chops

    Cuts a new Knockoff release by bumping the version, rolling release notes, tagging and shipping to the Chrome, Firefox and Apple stores with a per-store report.

    1.9k GitHub stars~1.2k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes

More from voyager-crew/voyager

  • Create Voyager Plugin

    voyager-crew/voyager

    Create or change a Voyager declarative plugin, site adapter, or native primitive.

    20k GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Release

    voyager-crew/voyager

    Prepare, publish, or recover a Voyager release. An agent skill from voyager-crew/voyager.

    20k GitHub stars~814 tokensUpdated today
    Auto-check passed

  • Voyager Contribute

    voyager-crew/voyager

    Prepare Voyager commits, pull requests, and contribution evidence, or claim an issue and check review readiness.

    20k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Update Safari Extension

    voyager-crew/voyager

    Build, reload, and verify Voyager in Safari for web-extension changes, native integration, or signed-app testing while preserving installed apps and extension data.

    20k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Issue Review

    voyager-crew/voyager

    Investigate or fix a referenced Voyager GitHub issue, within the requested delivery scope.

    20k GitHub stars~289 tokensUpdated today
    Auto-check passed

  • PR Description

    voyager-crew/voyager

    Write or rewrite a Voyager pull request description. An agent skill from voyager-crew/voyager.

    20k GitHub stars~182 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Verify In Browser

What does Verify In Browser do?

Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis. Verify In Browser is an agent skill from voyager-crew/voyager. Verify Voyager content-script or injected-CSS behavior in a live browser, including stale-build diagnosis.

When should I use Verify In Browser?

Verify In Browser fits situations like: tasks that involve Browser extensions.

How do I install Verify In Browser in Claude Code?

Run `npx skills add voyager-crew/voyager --skill verify-in-browser -a claude-code`. Or copy the skill folder (.agents/skills/verify-in-browser in voyager-crew/voyager) into .claude/skills/verify-in-browser in your project. Claude Code loads it when a task matches its description.

How do I install Verify In Browser in Codex?

Run `npx skills add voyager-crew/voyager --skill verify-in-browser -a codex`. Or copy the skill folder (.agents/skills/verify-in-browser in voyager-crew/voyager) into .agents/skills/verify-in-browser in your project. Codex loads it when a task matches its description.

Can I use Verify In Browser in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add voyager-crew/voyager --skill verify-in-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-in-browser, .gemini/skills/verify-in-browser, .github/skills/verify-in-browser and .opencode/skills/verify-in-browser in your project.

What does Verify In Browser need to run?

Going by SKILL.md and its folder, Verify In Browser needs the command-line tools its instructions call (bun).

Does Verify In Browser access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Verify In Browser safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Verify In Browser use?

Verify In Browser is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Verify In Browser use?

About 886 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Verify In Browser?

Skills that share tags, products or a category with Verify In Browser: Wxt Browser Extensions (vantezzen/skip-silence, 469 stars), Kimi Webbridge (MoonshotAI/kimi-code, 7.8k stars), Repomix Browser Extension Developer (yamadashy/repomix, 29k stars) and Deepseek Automation (zhu1090093659/deepseek-pp, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify In Browser?

voyager-crew (a GitHub organization) maintains it in voyager-crew/voyager, which has 20,338 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 10, 2026.

Source: voyager-crew/voyager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.